NavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation

arXiv:2609.30770 · cs.RO, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Comments: 8 pages,9 figures

Code: https://github.com/ModelTC/lightx2v

Project page: https://xinjiu612.github.io/NavGen

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generative Model — 11× in this paper · explained in 2 episodes
• Generative Models — 11× in this paper · explained in 2 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Sim-to-Real Gap — 9× in this paper · explained in 6 episodes
• Consistency — 8× in this paper · explained in 3 episodes
• Distillation — 8× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Embodied AI — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Transferability — 4× in this paper · explained in 4 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Decode — 3× in this paper · explained in 2 episodes
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency Distillation — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Flow Matching — 1× in this paper · explained in 7 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Wan: Open and Advanced Large-Scale Video Generative Models
• Qwen-Image Technical Report
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• Causal World Modeling for Robot Control
• VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
• FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model
• Scaling Robot Learning with Semantically Imagined Experience
• RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale
• Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
• Helios: Real Real-Time Long Video Generation Model

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving